USPersonalExpenditure

USPersonalExpenditure in R Markdown

KY

2020-04-23

##畫圖和指令相關語法
library(lattice)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(tidyr)
library(ggplot2)
library(grid)
library(gridExtra)

## 
## Attaching package: 'gridExtra'

## The following object is masked from 'package:dplyr':
## 
##     combine

##找出資料庫，使用資料
require(stats)
USPersonalExpenditure

##                       1940   1945  1950 1955  1960
## Food and Tobacco    22.200 44.500 59.60 73.2 86.80
## Household Operation 10.500 15.500 29.00 36.5 46.20
## Medical and Health   3.530  5.760  9.71 14.0 21.10
## Personal Care        1.040  1.980  2.45  3.4  5.40
## Private Education    0.341  0.974  1.80  2.6  3.64

dta <- USPersonalExpenditure
##網頁推薦USPersonalExpenditure使用medpolish，但不知道功用
medpolish(log10(dta))

## 1: 1.126317
## 2: 1.032421
## Final: 1.032421

## 
## Median Polish Results (Dataset: "log10(dta)")
## 
## Overall: 0.9872192
## 
## Row Effects:
##    Food and Tobacco Household Operation  Medical and Health       Personal Care 
##           0.7880270           0.4327608           0.0000000          -0.5606543 
##   Private Education 
##          -0.7319467 
## 
## Column Effects:
##       1940       1945       1950       1955       1960 
## -0.4288933 -0.2267967  0.0000000  0.1423128  0.3058289 
## 
## Residuals:
##                          1940       1945      1950      1955      1960
## Food and Tobacco     0.000000  0.0999105  0.000000 -0.053048 -0.142555
## Household Operation  0.030103 -0.0028516  0.042418  0.000000 -0.061167
## Medical and Health  -0.010551  0.0000000  0.000000  0.016596  0.031234
## Personal Care        0.019362  0.0968971 -0.037399 -0.037399  0.000000
## Private Education   -0.293625 -0.0399168  0.000000  0.017388  0.000000

##重新命名欄列名稱
colnames(dta)<-c("1940y","1945y","1950y","1955y","1960y")
rownames(dta)<-c("FT","HO","MH","PC","PE")
##看看命名後狀況
head(dta)

##     1940y  1945y 1950y 1955y 1960y
## FT 22.200 44.500 59.60  73.2 86.80
## HO 10.500 15.500 29.00  36.5 46.20
## MH  3.530  5.760  9.71  14.0 21.10
## PC  1.040  1.980  2.45   3.4  5.40
## PE  0.341  0.974  1.80   2.6  3.64

##將資料從寬資料轉長資料，才方便製圖
library(reshape2)

## 
## Attaching package: 'reshape2'

## The following object is masked from 'package:tidyr':
## 
##     smiths

dta1<- melt(dta)
##一樣觀察轉變後狀況
head(dta1)

##   Var1  Var2  value
## 1   FT 1940y 22.200
## 2   HO 1940y 10.500
## 3   MH 1940y  3.530
## 4   PC 1940y  1.040
## 5   PE 1940y  0.341
## 6   FT 1945y 44.500

names(dta1)

## [1] "Var1"  "Var2"  "value"

##命名新的欄列名稱
colnames(dta1)<- c("category","year", "expenditure")
head(dta1)

##   category  year expenditure
## 1       FT 1940y      22.200
## 2       HO 1940y      10.500
## 3       MH 1940y       3.530
## 4       PC 1940y       1.040
## 5       PE 1940y       0.341
## 6       FT 1945y      44.500

##大略看一下圖形關係
library(ggfortify)
autoplot(with(dta1, 
              lm(expenditure ~ category))) +
theme_bw()

##雖然簡單分出category，year，expenditure，但覺得ggplot語法不熟悉，許多圖形常跑error
ggplot(dta1, aes(category, expenditure)) +
  geom_boxplot(col='gray') +
  geom_point() +
  facet_wrap(. ~ year) +
  theme_bw()